Background and Objectives: Autism spectrum disorder (ASD) is a neurodevelopmental condition traditionally diagnosed through subjective behavioral assessments. Resting-state functional MRI (rs-fMRI) provides a potential pathway for objective neuroimaging biomarker discovery; however, existing deep learning methods often struggle to integrate neurobiological priors with data-driven representations. This study aimed to address these limitations by developing a biologically interpretable graph-learning framework for rs-fMRI-based ASD classification. Methods: We propose ASD-FCGCN, a biologically informed graph convolutional network validated on 871 subjects from the ABIDE dataset. The method systematically integrates neurobiological priors with graph learning. Specifically, prior-weighted functional connectivity matrices are constructed to generate hemisphere-specific representations. A Pairwise Association Encoder (PAE) is employed to estimate inter-subject phenotypic relationships, transforming similarity weights into channel-wise gating signals to dynamically regulate graph convolution. Furthermore, a corpus callosum-inspired interaction mechanism is introduced to enable bidirectional information exchange between hemispheres, thereby synthesizing whole-brain features for classification. Results: Experimental results demonstrated that ASD-FCGCN achieved strong classification performance under subject-level 10-fold cross-validation, with an accuracy of 94.60% ± 3.04%, an AUC of 97.66% ± 1.82%, a sensitivity of 94.66% ± 3.72%, a specificity of 94.52% ± 4.16%, and an F1-score of 94.96% ± 2.81%. Conclusion: The results indicate that integrating neurobiological priors, phenotype-guided convolution, and cross-hemispheric coordination can improve subject-level rs-fMRI-based ASD classification. The proposed model provides a promising computational framework for ASD auxiliary diagnosis and offers biologically informed model-level interpretability by integrating ASD-related prior ROIs, phenotype-guided graph propagation, and hemisphere-specific interaction modeling.
This paper develops an asynchronous distributed protocol for formation-containment flocking of discrete-time multi-agent systems, addressing moving leaders, cooperative-competitive interactions modeled by signed digraphs, and nonuniform private update schedules within a single design. Using only local neighbor information, each follower is driven to a prescribed barycentric position inside the translating convex hull of the leaders while aligning its velocity with the common leader velocity. The protocol couples absolute-value weighted velocity averaging for flocking with signed relative-position feedback for formation-containment. Convergence is analyzed through the theory of infinite products of sub-stochastic matrices, which yields explicit conditions linking the network topology (positive-path reachability), the control gains, the signed interaction weights, and the inter-update bound, and guarantees geometric convergence. Numerical examples with diamond and pentagram formations confirm the theoretical results and demonstrate scalability.
Starch retrogradation, driven by reassociation and recrystallization of gelatinized amylose and amylopectin chains, induces undesirable firming, syneresis, and sensory deterioration, ultimately shortening the shelf-life of starch-based foods. Enzymatic modification has emerged as a promising route to retard retrogradation, but its efficacy critically depends on the structural features targeted by the enzyme, the susceptibility of the starch substrate, and the accessibility of catalytic sites. This review systematically interprets the structure-dependent mechanisms underlying enzymatic retrogradation regulation, covering the differential regulatory patterns of various enzyme systems. This review further clarifies the essential distinction between substrate structural susceptibility and enzyme catalytic accessibility, and summarizes advanced modification strategies based on porous starch construction and controlled starch swelling to optimize enzyme-substrate interfacial contact efficiency. In addition, mainstream detection techniques are compared based on the different levels of the studied starch structure. Finally, the practical applicability of enzymatic anti-retrogradation technologies in diverse staple and processed starch-based food systems are also summarized. We propose that the key design principle is controlled structural remodeling enabled by enzyme action within a defined processing window, rather than indiscriminate starch degradation. This work provides systematic theoretical insights and practical guidance for the quality stabilization and shelf-life extension of starch-based food products.
White balance (WB) correction for sRGB images captured under multiple illuminations remains challenging due to spatially varying and nonlinear color casts. Existing sRGB-domain WB methods, relying on global adjustment or content-dependent priors, struggle in such scenes because they lack spatial adaptivity correction and explicit illumination guidance. Further, both types of methods lack the consideration of multi-illumination characteristics due to only single-illumination data being available for supervision. To address these limitations, we propose AdaWBNet, an illumination-guided spatially adaptive WB framework formulated under a Maximum A Posteriori estimation paradigm. Within this framework, learnable illumination prototypes serve as priors that capture representative single-illumination patterns, and a K-means cross-attention module enhances these prototypes by assigning local features of multi-illumination inputs to similar prototypes. Then, guided by the illumination prototypes, the likelihood term employs query-adaptive layers to achieve illumination-aware, spatially adaptive color correction. This design enables AdaWBNet to achieve both spatially adaptive color correction and illumination guidance using only single-illumination supervision, thereby allowing it to effectively handle complex multi-illumination scenes. Extensive experiments demonstrate that AdaWBNet outperforms state-of-the-art methods on multi-illumination benchmarks, achieving spatially consistent and perceptually faithful results. The code is available at here.
In this paper, we propose a partially linear additive single-index model. A new loss function is introduced to construct doubly robust and efficient estimation of the regression parameters. The estimators for each nonparametric function are also constructed and their uniform convergence rates are obtained. The asymptotic distributions of all estimators are derived. The bias-corrected empirical likelihood ratios are constructed, and it is shown that each proposed ratio converges in distribution to a standard chi-square variable. The obtained results can be directly used to construct confidence regions of the regression parameters and pointwise confidence intervals for the nonparametric functions. Simulation study and real data analysis demonstrate the robustness and effectiveness of the proposed estimators.
